-
Je něco špatně v tomto záznamu ?
From discourse to pathology: Automatic identification of Parkinson's disease patients via morphological measures across three languages
E. Eyigoz, M. Courson, L. Sedeño, K. Rogg, JR. Orozco-Arroyave, E. Nöth, S. Skodda, N. Trujillo, M. Rodríguez, J. Rusz, E. Muñoz, JF. Cardona, E. Herrera, E. Hesse, A. Ibáñez, G. Cecchi, AM. García
Jazyk angličtina Země Itálie
Typ dokumentu časopisecké články, práce podpořená grantem
Grantová podpora
R01 AG057234
NIA NIH HHS - United States
- MeSH
- jazyk (prostředek komunikace) * MeSH
- kognice MeSH
- lidé MeSH
- Parkinsonova nemoc * MeSH
- řeč MeSH
- strojové učení MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
Embodied cognition research on Parkinson's disease (PD) points to disruptions of frontostriatal language functions as sensitive targets for clinical assessment. However, no existing approach has been tested for crosslinguistic validity, let alone by combining naturalistic tasks with machine-learning tools. To address these issues, we conducted the first classifier-based examination of morphological processing (a core frontostriatal function) in spontaneous monologues from PD patients across three typologically different languages. The study comprised 330 participants, encompassing speakers of Spanish (61 patients, 57 matched controls), German (88 patients, 88 matched controls), and Czech (20 patients, 16 matched controls). All subjects described the activities they perform during a regular day, and their monologues were automatically coded via morphological tagging, a computerized method that labels each word with a part-of-speech tag (e.g., noun, verb) and specific morphological tags (e.g., person, gender, number, tense). The ensuing data were subjected to machine-learning analyses to assess whether differential morphological patterns could classify between patients and controls and reflect the former's degree of motor impairment. Results showed robust classification rates, with over 80% of patients being discriminated from controls in each language separately. Moreover, the most discriminative morphological features were associated with the patients' motor compromise (as indicated by Pearson r correlations between predicted and collected motor impairment scores that ranged from moderate to moderate-to-strong across languages). Taken together, our results suggest that morphological patterning, an embodied frontostriatal domain, may be distinctively affected in PD across languages and even under ecological testing conditions.
Departamento de Estudios Psicológicos Universidad Icesi Cali Colombia
Department of Neurology Knappschaftskrankenhaus Ruhr University Bochum Germany
Department of Psychology Faculty of Arts Charles University Prague Prague Czech Republic
Department of Psychology Université de Montréal CRIUGM Research Center Montréal Canada
Department of Social Psychology University of Würzburg Würzburg Germany
Faculty of Education National University of Cuyo Mendoza Argentina
GITA Lab Faculty of Engineering University of Antioquia Medellín Colombia
Global Brain Health Institute University of California San Francisco United States
IBM Research T J Watson Research Center New York USA
Instituto de Psicología Universidad del Valle Cali Colombia
National Institute of Mental Health Prague Czech Republic
National Scientific and Technical Research Council Buenos Aires Argentina
Neuroscience Group Faculty of Medicine University of Antioquia Medellín Colombia
Pattern Recognition Lab Friedrich Alexander Universität Erlangen Nürnberg Germany
School of Public Health University of Antioquia Medellín Colombia
Citace poskytuje Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc21019867
- 003
- CZ-PrNML
- 005
- 20210830101451.0
- 007
- ta
- 008
- 210728s2020 it f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.1016/j.cortex.2020.08.020 $2 doi
- 035 __
- $a (PubMed)32992069
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a it
- 100 1_
- $a Eyigoz, Elif $u IBM Research, T. J. Watson Research Center, New York, USA
- 245 10
- $a From discourse to pathology: Automatic identification of Parkinson's disease patients via morphological measures across three languages / $c E. Eyigoz, M. Courson, L. Sedeño, K. Rogg, JR. Orozco-Arroyave, E. Nöth, S. Skodda, N. Trujillo, M. Rodríguez, J. Rusz, E. Muñoz, JF. Cardona, E. Herrera, E. Hesse, A. Ibáñez, G. Cecchi, AM. García
- 520 9_
- $a Embodied cognition research on Parkinson's disease (PD) points to disruptions of frontostriatal language functions as sensitive targets for clinical assessment. However, no existing approach has been tested for crosslinguistic validity, let alone by combining naturalistic tasks with machine-learning tools. To address these issues, we conducted the first classifier-based examination of morphological processing (a core frontostriatal function) in spontaneous monologues from PD patients across three typologically different languages. The study comprised 330 participants, encompassing speakers of Spanish (61 patients, 57 matched controls), German (88 patients, 88 matched controls), and Czech (20 patients, 16 matched controls). All subjects described the activities they perform during a regular day, and their monologues were automatically coded via morphological tagging, a computerized method that labels each word with a part-of-speech tag (e.g., noun, verb) and specific morphological tags (e.g., person, gender, number, tense). The ensuing data were subjected to machine-learning analyses to assess whether differential morphological patterns could classify between patients and controls and reflect the former's degree of motor impairment. Results showed robust classification rates, with over 80% of patients being discriminated from controls in each language separately. Moreover, the most discriminative morphological features were associated with the patients' motor compromise (as indicated by Pearson r correlations between predicted and collected motor impairment scores that ranged from moderate to moderate-to-strong across languages). Taken together, our results suggest that morphological patterning, an embodied frontostriatal domain, may be distinctively affected in PD across languages and even under ecological testing conditions.
- 650 _2
- $a kognice $7 D003071
- 650 _2
- $a lidé $7 D006801
- 650 12
- $a jazyk (prostředek komunikace) $7 D007802
- 650 _2
- $a strojové učení $7 D000069550
- 650 12
- $a Parkinsonova nemoc $7 D010300
- 650 _2
- $a řeč $7 D013060
- 655 _2
- $a časopisecké články $7 D016428
- 655 _2
- $a práce podpořená grantem $7 D013485
- 700 1_
- $a Courson, Melody $u Department of Psychology, Université de Montréal, CRIUGM Research Center, Montréal, Canada
- 700 1_
- $a Sedeño, Lucas $u National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina
- 700 1_
- $a Rogg, Katharina $u Department of Social Psychology, University of Würzburg, Würzburg, Germany
- 700 1_
- $a Orozco-Arroyave, Juan Rafael $u Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen-Nürnberg, Germany; GITA Lab, Faculty of Engineering, University of Antioquia (UdeA), Medellín, Colombia
- 700 1_
- $a Nöth, Elmar $u Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen-Nürnberg, Germany
- 700 1_
- $a Skodda, Sabine $u Department of Neurology, Knappschaftskrankenhaus, Ruhr-University, Bochum, Germany
- 700 1_
- $a Trujillo, Natalia $u Neuroscience Group, Faculty of Medicine, University of Antioquia (UdeA), Medellín, Colombia; School of Public Health, University of Antioquia (UdeA), Medellín, Colombia
- 700 1_
- $a Rodríguez, Mabel $u National Institute of Mental Health, Prague, Czech Republic; Department of Psychology, Faculty of Arts, Charles University in Prague, Prague, Czech Republic
- 700 1_
- $a Rusz, Jan $u Department of Circuit Theory, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic
- 700 1_
- $a Muñoz, Edinson $u Departamento de Lingüística y Literatura, Facultad de Humanidades, Universidad de Santiago de Chile, Santiago, Chile
- 700 1_
- $a Cardona, Juan F $u Instituto de Psicología, Universidad del Valle, Cali, Colombia
- 700 1_
- $a Herrera, Eduar $u Departamento de Estudios Psicológicos, Universidad Icesi, Cali, Colombia
- 700 1_
- $a Hesse, Eugenia $u National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina; Universidad de San Andrés, Buenos Aires, Argentina
- 700 1_
- $a Ibáñez, Agustín $u National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina; Universidad de San Andrés, Buenos Aires, Argentina; Universidad Autónoma del Caribe, Barranquilla, Colombia; Center for Social and Cognitive Neuroscience (CSCN), School of Psychology, Universidad Adolfo Ibáñez, Santiago de Chile, Chile; Global Brain Health Institute, University of California, San Francisco, United States
- 700 1_
- $a Cecchi, Guillermo $u IBM Research, T. J. Watson Research Center, New York, USA
- 700 1_
- $a García, Adolfo M $u National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina; Departamento de Lingüística y Literatura, Facultad de Humanidades, Universidad de Santiago de Chile, Santiago, Chile; Universidad de San Andrés, Buenos Aires, Argentina; Global Brain Health Institute, University of California, San Francisco, United States; Faculty of Education, National University of Cuyo (UNCuyo), Mendoza, Argentina. Electronic address: adolfomartingarcia@gmail.com
- 773 0_
- $w MED00001234 $t Cortex; a journal devoted to the study of the nervous system and behavior $x 1973-8102 $g Roč. 132, č. - (2020), s. 191-205
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/32992069 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y p $z 0
- 990 __
- $a 20210728 $b ABA008
- 991 __
- $a 20210830101451 $b ABA008
- 999 __
- $a ok $b bmc $g 1690632 $s 1140313
- BAS __
- $a 3
- BAS __
- $a PreBMC
- BMC __
- $a 2020 $b 132 $c - $d 191-205 $e 20200908 $i 1973-8102 $m Cortex $n Cortex $x MED00001234
- GRA __
- $a R01 AG057234 $p NIA NIH HHS $2 United States
- LZP __
- $a Pubmed-20210728
